Model for Determining Noise Level Depending on Traffic Volume at Intersections

Abstract

The negative external effects caused by traffic growth have been recognized as the main factors that degrade city quality of life. Therefore, research around the world is being conducted to understand the impact of traffic better and find adequate measures to reduce the negative impact of traffic growth. The central part of this research consists of mathematical models for simulating the negative consequences of congestion and noise pollution. Four non-linear models for determining noise levels as a function of traffic flow parameters (intensity and structure) in the urban environment were developed. The non-linear models, including two artificial neural networks and two random forest models, were developed according to the experimental measurements in Novi Sad, Serbia, in 2019. These non-linear models showed high anticipation accuracy of the equivalent continuous sound level (Laeq), with R2 values of 0.697, 0.703, 0.959 and 0.882, respectively. According to the developed ANN models, global sensitivity analysis was performed, according to which the number of buses at crossings was the most positively signed influential parameter in Laeq evaluation, while the lowest Laeq value was reached during nighttime. The locations occupied by frequent traffic such as Futoska and Temerinska positively influenced the Laeq value.

Heavy metal concentrations in the soil near illegal landfills in the vicinity of agricultural areas—artificial neural network approach

“…A multi-layer perceptron (MLP) structure, including three layers (input, hidden, and output), was used for modeling eight ANN models for the prediction of As, Cd, Cr, Cu, Ni, Pb, Zn, and Hg concentrations in the soil near illegal landfills in the vicinity of agricultural areas based on landfill size, municipality size, the number of residents, plant species, soil, and landforms types. According to the known references, the ANN models were confirmed as completely fitted to evaluating nonlinear functions (Ćurčić et al 2022;Ruškić et al 2022). Input data were continuously introduced to the network; however, before calculation, the input and output database was normalized according to the min-max formula to enhance the behavior of the ANN models (Rajković et al 2022).…”

Unlocking the Potential of the ANN Optimization in Sweet Potato Varieties Drying Processes

“…As presented in Table 6 , the validation of the artificial neural network (ANN) model was conducted through both goodness-of-fit evaluation and residual analysis [ 51 ]. The results from the residual analysis revealed a random occurrence of residuals, underscoring the excellent fit of the model to the data.…”

Osmotic Dehydration Model for Sweet Potato Varieties in Sugar Beet Molasses Using the Peleg Model and Fitting Absorption Data Using the Guggenheim–Anderson–de Boer Model

“…In terms of error analysis, the accuracy of the developed models was evaluated through several key metrics, i.e., coefficient of determination ( r 2 ), reduced chi-square ( χ 2 ), mean bias error ( MBE ), root mean square error ( RMSE ), mean percentage error ( MPE ), the sum of squared errors ( SSE ), and average absolute relative deviation ( AARD ). These widely used parameters were employed to assess the validity of the models [ 45 ], as follows: where x exp,i stands for the experimental values; x pre,i are the predicted values calculated by the model; and N and n are the number of observations and constants, respectively.…”